Abstract
Indoor air quality (IAQ) problems in school environments are very common and have significant impacts on students' performance, development and health. Indoor air conditions depend on the adopted ventilation practices, which in Mediterranean countries are essentially based on natural ventilation controlled through manual window opening. Citizen science projects directed to school communities are effective strategies to promote awareness and knowledge acquirement on IAQ and adequate ventilation management. Our multidisciplinary research team has developed a framework-SchoolAIR-based on low-cost sensors and a scalable IoT system architecture to support the improvement of IAQ in schools. The SchoolAIR framework is based on do-it-yourself sensors that continuously monitor air temperature, relative humidity, concentrations of carbon dioxide and particulate matter in school environments. The framework was tested in the classrooms of University Fernando Pessoa, and its deployment and proof of concept took place in a high school in the north of Portugal. The results obtained reveal that CO2 concentrations frequently exceed reference values during classes, and that higher concentrations of particulate matter in the outdoor air affect IAQ. These results highlight the importance of real-time monitoring of IAQ and outdoor air pollution levels to support decision-making in ventilation management and assure adequate IAQ. The proposed approach encourages the transfer of scientific knowledge from universities to society in a dynamic and active process of social responsibility based on a citizen science approach, promoting scientific literacy of the younger generation and enhancing healthier, resilient and sustainable indoor environments.

Abstract
We spend about one-third of our life either sleeping or attempting to do so. Sleeping is a key aspect for most human body processes, affecting physical and mental health and the ability to fight diseases, develop immunity and control metabolism. Therefore, monitoring human sleep quality is extremely important for the detection of possible sleep disorders. Several technologies exist to achieve this goal, however, most of them are expensive proprietary systems, some require hospitalization and many use intrusive equipment that can, by itself, affect sleep quality. This paper presents an intelligent system, a complete low-cost hardware and software solution, for monitoring the sleep quality of an individual in a home environment. User privacy is guaranteed as all processing is done at the edge and no audio or video is stored. This system monitors several fundamental aspects of sleeping periods in real-time using a low cost single-board computer for processing, a camera for body motion detection (MD module) and for eye/sleep status detection (SSD module), and a microphone for audio recognition (AUDR module) of breath pattern analysis and snore detection. It can be strategically placed near the bed to avoid interfering with the natural sleep pattern. For each sleeping period, the system produces a final report that can be a valuable aid for improving the sleeping health of the monitored person. Functional unitary tests were carried successfully on the selected, low-cost, hardware platform (Raspberry Pi). The entire process was validated by an expert clinical psychologist, ensuring the reliability and effectiveness of the system. The visual and sound modules use sophisticated computer vision and machine learning techniques suitable for edge computing devices. Each of the system’s features have been independently tested, using properly organized audio and video datasets and the well established metrics of precision, recall and F1 score, to evaluate the binary classifiers in each of the three modules. The accuracy values obtained where 90.2% (MD), 79.1% (SSD) and 81.3% (AUDR), demonstrating the great application potential of our solution. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

Abstract
In Portugal, more than 98% of domestic cooking oil is disposed of improperly every day. This avoids recycling/reconverting into another energy. Is also may become a potential harmful contaminant of soil and water. Driven by the utility of recycled cooking oil, and leveraging the exponential growth of ubiquitous computing approaches, we propose an IoT smart solution for domestic used cooking oil (UCO) collection bins. We call this approach SWAN, which stands for Smart Waste Accumulation Network. It is deployed and evaluated in Portugal. It consists of a countrywide network of collection bin units, available in public areas. Two metrics are considered to evaluate the system's success: (i) user engagement, and (ii) used cooking oil collection efficiency. The presented system should (i) perform under scenarios of temporary communication network failures, and (ii) be scalable to accommodate an ever-growing number of installed collection units. Thus, we choose a disruptive approach from the traditional cloud computing paradigm. It relies on edge node infrastructure to process, store, and act upon the locally collected data. The communication appears as a delay-tolerant task, i.e., an edge computing solution. We conduct a comparative analysis revealing the benefits of the edge computing enabled collection bin vs. a cloud computing solution. The studied period considers four years of collected data. An exponential increase in the amount of used cooking oil collected is identified, with the developed solution being responsible for surpassing the national collection totals of previous years. During the same period, we also improved the collection process as we were able to more accurately estimate the optimal collection and system's maintenance intervals.

Abstract
The aim of this chapter focuses on featuring firmed IoT architecture paradigms and advocating, knowingly in concrete use cases, the combined use of such architecture categories. It is common knowledge that the growing demand for embedded processing, interconnection, and integration facilities in everyday objects is being driven by a multitude of IoT projects. The smart cities, smart agriculture, manufacturing, and industrial automation areas are some of the most important application grounds. Equally important is the medical sector where specially framed in this publication, the personal home healthcare scenarios gain enormous relevance due to the potential of IoT technology application. It is also becoming clear that the IoT-trending efforts are compelling researchers into the concurrent combination of multiple IoT-computing architecture types or paradigms, to know: wide-range cloud-computing architectures, local-spread fog-computing architectures, and spottily scattered edge-computing architectures. This chapter focuses on identifying the major goals and benefits of each of these architectures classes; describing the relevant state of the art projects, which apply such architecture categories in home healthcare settings; and finally, pinpointing our own experience with home e-health demonstrative use case scenarios, where the benefits of using each of these architecture types become evident, and the concurrent combination of such IoT architectures inevitable. © 2021 Elsevier Inc.

Abstract
Absenteeism is a major problem faced particularly by companies with a large number of employees. Therefore, the existence of absenteeism prediction tools is essential for such companies depending on intensive human-resources. This paper focuses on using machine learning technologies for predicting the absences of employees from work. More precisely, a few prediction models were tuned and tested with 241 features extracted from a population of 13.805 employees. This target population was sampled from the help desk work force of a major Brazilian phone company. The features were extracted from the profile of the help desk agents and then filtered by processes of correlation and feature selection. The selected features were then used to compare absenteeism prediction given by different classification algorithm (cf. Random Forest, Multilayer Perceptron, Support Vector Machine, Naive Bayes, XGBoost and Long Short Term Memory). The parameterization of these ML models was also studied to reach the classifier best suited for the prediction problem. Such parameterizations were tuned through the use of evolutionary algorithms, from which considerable precision was reached, the best being 72% (XGBoost) and 71% (Random Forest). © 2019, Springer Nature Switzerland AG.